Redundant Array of Independent Memory Devices
- 20 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Architecture Letters
- Vol. 22 (2) , 181-184
Abstract
DRAM memory reliability is increasingly a concern as recent studies found. In this paper, we propose RAIMD (Redundant Array of Independent Memory Devices), an energy-efficient memory organization with RAID-like error protection. In this organization, each memory device works as an independent memory module to serve a whole memory request and to support error detection and error recovery. It relies on the high data rate of modern memory device to minimize the performance impact of increased data transfer time. RAIMD provides chip-level error protection similar to ChipKill but with significant energy savings. Our simulation results indicate that RAIMD can save memory energy by 26.3% on average with a small performance overhead of 5.3% on DDR5-4800 memory systems for SPEC2017 multi-core workloads.Keywords
Funding Information
- National Science Foundation (CCF-1618104, CCF-1643271)
This publication has 10 references indexed in Scilit:
- Dvé: Improving DRAM Reliability and Performance On-Demand via Coherent Replication2021
- Redundant Memory Array Architecture for Efficient Selective Protection2017
- XED: Exposing On-Die Error Detection Information for Strong Memory Reliability2016
- Modeling the implications of DRAM failures and protection techniques on datacenter TCO2015
- Partial Parity Cache and Data Cache Management Method to Improve the Performance of an SSD-Based RAIDIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2013
- A study of DRAM failures in the field2012
- IBM zEnterprise redundant array of independent memory subsystemIBM Journal of Research and Development, 2012
- System implications of memory reliability in exascale computing2011
- Mini-rank: Adaptive DRAM architecture for improving memory power efficiency2008
- Using SimPoint for accurate and efficient simulationACM SIGMETRICS Performance Evaluation Review, 2003